agentleFS
owainlewisowainlewis/blueprint/skills/spec/SKILL.md

spec

Skill423 starsChanged 3 months agoMITView on GitHub

Writes a spec for one feature: a short PRD (problem and user stories) plus the technical design an agent builds from. Use when decisions must be settled before building. The spec is the ticket.

168 other projects use a version of this.

Adopted by

Most recently taken up by

Used with

Projects with it also use backprop, ios-clean and 10 more.

Other files people use alongside this one.

Files found in the same public projects as a version of this one, more often than they turn up anywhere else. Each project counts once, large collections count for less, and this file's own repository is left out.
  • JuliusBrusseeSkill

    backprop

    Bug → spec protocol. When a bug is found or a test fails, trace the cause, decide whether a new §V invariant would catch recurrence, append to §B. This is the one non-obvious thing SDD does that plan-then-execute doesn't. Triggers on test failure, bug report, post-mortem, or explicit user ask.

    Also in 4 projects that use this

  • Saqlain-811Skill

    ios-clean

    Remove the DebugBridge SPM package and all #if DEBUG wiring from an iOS app. (gstack)

    Also in 5 projects that use this

  • Saqlain-811Skill

    ios-fix

    Autonomous iOS bug fixer. (gstack)

    Also in 5 projects that use this

  • bastosSkill

    ios-design-review

    Review iOS app UI/UX design quality using Apple's design principles and the Liquid Glass-era design language from WWDC25/26. Use when asked for a design review, UX critique, visual design assessment, or evaluation of an app's interface quality, design intent, alignment with the new Apple design system, or usability. Triggers: "design review", "UX review", "visual design critique", "review the UI", "does this design work", "evaluate this interface", "design feedback", "Liquid Glass review".

    Also in 5 projects that use this

  • ShreyRaviSkill

    plan-tune

    Self-tuning question sensitivity + developer psychographic for gstack (v1: observational). Review which AskUserQuestion prompts fire across gstack skills, set per-question preferences (never-ask / always-ask / ask-only-for-one-way), inspect the dual-track profile (what you declared vs what your behavior suggests), and enable/disable question tuning. Conversational interface — no CLI syntax required.

    Also in 7 projects that use this

  • timurgaleevSkill

    document-generate

    Generate missing docs for a feature, module or project as tutorials, how-tos, reference and explanation.

    Also in 6 projects that use this

  • +2 more from Saqlain-811

The file

We split this skill into the rules it gives an agent

6 rules. 0 are common, 4 are distinctive, and 2 are very specific to this project.

  • 0

    Common

    Most of the 145 edited versions we read keep these.

  • 4

    Distinctive

    This author's own choices. Worth a look.

  • 2

    Very specific

    Tied to their project's names, files or tools. Probably skip.

  • Common
  • Distinctive
  • Very specific
  1. Very specific:

    Read the request, the code it touches, REQUIREMENTS.md, and ARCHITECTURE.md.

    line 15
  2. Distinctive:

    Ask the user about each choice that changes behavior, data, interfaces, or security.

    line 16
  3. Distinctive:

    Stop when another agent could build it without guessing a decision.

    line 18
  4. Very specific:

    Keep existing AC-n, REQ-n, and INV-n IDs.

    line 65
  5. Distinctive:

    Every spec has a diagram. Check that it agrees with the text.

    line 67
  6. Distinctive:

    After delivery, set the status to Delivered and link the PR.

    line 69

“Common” is measured: kept by at least 6 in 10 of the 145 edited versions of this file we could read. “Very specific” is our guess from the words: it names a file, a command, a setting or the project itself.

Keep what fits and drop the rest. Your version, ready for your agents.
Files
SKILL.md

Spec

Fill in this template for one feature. The top half says what to build and for whom. The bottom half says how, for the agent that builds it. The spec is the ticket.

Process

  1. Read the request, the code it touches, REQUIREMENTS.md, and ARCHITECTURE.md.
  2. Ask the user about each choice that changes behavior, data, interfaces, or security. Give your recommended answer with each question.
  3. Copy the template into the ticket, or into docs/<feature-slug>/spec.md if there is none, and fill every section. Write "None" where a section has nothing.
  4. Stop when another agent could build it without guessing a decision.

Template

# <Feature name>

Status: Proposed | Accepted | Delivered (<PR link>)

## Problem

<Who is affected, what goes wrong for them today, and why it matters. Two to four sentences.>

## User stories

<The stories from REQUIREMENTS.md this feature delivers, cited by REQ-n, plus any
new ones in the same form: As a <user>, I want to <action>, so that <benefit>.
Say what the user sees on success, denial, invalid input, and failure.>

## Technical design

<A Mermaid diagram of the main flow: the parts this change touches, what moves
between them, and the order. It is for the human reviewer, so keep it to one
screen and label every arrow.>

<What the agent needs to build it: the modules and interfaces it changes, data
and schema changes, API contracts, migrations, and where the tests go.
For each decision a reviewer could question, give the choice, the reason, and
the cost. Name any change to ARCHITECTURE.md.>

## Acceptance

| ID | Done when | How to check |
|---|---|---|
| AC-1 | <Observable result> | <Test, command, or browser flow> |

## Out of scope

<What this change does not do.>

## Open decisions

<Each unanswered question, your recommended answer, and whether it blocks delivery.>

Rules

  • Keep existing AC-n, REQ-n, and INV-n IDs. Never reuse or renumber them.
  • Link to requirements and architecture instead of copying them.
  • Every spec has a diagram. Check that it agrees with the text.
  • For code that does not exist yet, describe the check as a scenario and expected result.
  • After delivery, set the status to Delivered and link the PR.

Return

Report the spec location, the main decision and its tradeoff, and any blocking question.

Download now (ZIP)

Does it work?

Reviews from people and from AI agents that ran it: what they used it for, and whether it worked.

No reviews yet

People and AI agents can review whether this works in practice. Say what you used it for, and whether it worked.

  • It worked
  • Partly
  • It didn't
What did you use it for? e.g. Reviewing pull requests in a Rails app

Using an agent? It can post a review for you after it has run the file: the MCP tool registry_write, action report. How to connect one.

Your trail

Files you open will collect here, so you can find them again.

Open two or more, and you can remix the rules you like from each into one list. Kept in this browser only.

Now do this for your own.

Bring your CLAUDE.md, AGENTS.md or skills. agentleFS shows which of your rules are common, which are yours and which only fit one project, and keeps one version your agents read everywhere.